YOLOv4_Drone: UAV image target detection based on an improved YOLOv4 algorithm. (July 2021)

• Record Type: Journal Article
• Authors: Tan, Li; Lv, Xinyue; Lian, Xiaofeng; Wang, Ge
• Is Part Of: Computers & electrical engineering. Volume 93(2021)
• Publication Date: 2021-07
• Subjects: UAV -- Target detection -- YOLOv4 -- Attention mechanism; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2021.107261
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Extract features of different scales, improve the feature extraction capability of the network. Detect small targets in UAV images with a complex background was increased by adding a receptive field module. The ultra-lightweight subspace attention mechanism is used to derive different attention feature maps for each subspace of the feature map for multi-scale feature representation. Soft non-maximum suppression is introduced in the detection stage to minimize the occurrence of missed targets due to occlusion. Abstract: Advanced communications and networks have greatly improved the user experience, and unmanned aerial vehicle (UAV) are an important technology that supports people's daily life and military activities. Since target detection in UAV images is complicated by a complex background, small targets, and target occlusion, the detection accuracy of the You Only Look Once(YOLO) v4 algorithm is relatively low. Therefore, hollow convolution is used to resample the feature image to improve the feature extraction and target detection performance. In addition, the ultra-lightweight subspace attention mechanism (ULSAM) is used to derive different attention feature maps for each subspace of the feature map for multi-scale feature representation. Finally, soft non-maximum suppression (Soft-NMS) is introduced to minimize the occurrence of missed targets due to occlusion. The experimental results prove that the proposed UAV image target detection model (YOLOv4_Drone) has 5% improved to the YOLOv4 algorithm, demonstrating the effectiveness of the method. Graphical abstract: Image, graphical abstract